Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.7715. Min Act: -0.0000

Data Index: 112699 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.8507. Min Act: -0.0000

Data Index: 410494 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.6548. Min Act: -0.0000

Data Index: 726469 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.3262. Min Act: -0.0000

Data Index: 18425 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.3168. Min Act: -0.0000

Data Index: 588567 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.4278. Min Act: -0.0000

Data Index: 919095 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1331665 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.1969. Min Act: -0.0000

Data Index: 748329 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.3053. Min Act: -0.0000

Data Index: 560725 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.1789. Min Act: -0.0000

Data Index: 155245 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2983. Min Act: -0.0000

Data Index: 790940 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.1618. Min Act: -0.0000

Data Index: 751632 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2993. Min Act: -0.0000

Data Index: 944315 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.1772. Min Act: -0.0000

Data Index: 332 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2688. Min Act: -0.0000

Data Index: 316414 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2815. Min Act: -0.0000

Data Index: 479820 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.3931. Min Act: -0.0000

Data Index: 541754 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2634. Min Act: -0.0000

Data Index: 705613 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.1451. Min Act: -0.0000

Data Index: 696866 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.8507. Min Range: -2.8507

Max Act: 2.2657. Min Act: -0.0000

Data Index: 1028797 (C4 (Web Text))

Max Activating Token Index: 821